-
Notifications
You must be signed in to change notification settings - Fork 12
Pull requests: ai-dynamo/snapshot
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
📝 add restore compatibility checker design
#226
opened Sep 6, 2026 by
leeZardNav
Collaborator
Loading…
feat(agent): orchestrate the cuinterpose coordinator around checkpoint and restore
#223
opened Sep 4, 2026 by
galletas1712
Contributor
•
Draft
feat: deliver the cuinterpose shim to annotated Pods
#222
opened Sep 4, 2026 by
galletas1712
Contributor
•
Draft
test(agent): cuinterpose GPU tests
#220
opened Sep 4, 2026 by
galletas1712
Contributor
•
9/9
•
Draft
feat(agent): checkpoint CUDA multicast state
#219
opened Sep 4, 2026 by
galletas1712
Contributor
•
8/9
•
Draft
feat(agent): checkpoint and restore POSIX CUDA VMM state
#218
opened Sep 4, 2026 by
galletas1712
Contributor
•
7/9
•
Draft
feat(agent): track POSIX CUDA VMM state
#217
opened Sep 4, 2026 by
galletas1712
Contributor
•
6/9
•
Draft
feat(agent): cuinterpose coordinator
#216
opened Sep 4, 2026 by
galletas1712
Contributor
•
5/9
•
Draft
feat(agent): cuinterpose shim symbol resolution and forwarding
#215
opened Sep 4, 2026 by
galletas1712
Contributor
•
4/9
•
Draft
feat: launch multi-GPU sources under cuda-checkpoint --launch-job
#213
opened Sep 4, 2026 by
galletas1712
Contributor
•
2/9
•
Draft
feat(agent): package the cuinterpose shim and coordinator
#212
opened Sep 4, 2026 by
galletas1712
Contributor
•
1/9
•
Draft
fix(agent): build criu and restore tar against an older glibc floor
#179
opened Sep 2, 2026 by
oleg-kushniriov
Contributor
Loading…
ci(e2e): run framework checkpoint/restore tests on pull requests and nightly
#176
opened Sep 2, 2026 by
oleg-kushniriov
Contributor
Loading…
test(e2e): checkpoint/restore tests for the framework guide workloads
#175
opened Sep 2, 2026 by
oleg-kushniriov
Contributor
Loading…
fix(agent): restore restarted destination containers
#174
opened Sep 2, 2026 by
galletas1712
Contributor
Loading…
perf(cuda): restore CustomStorage ranks concurrently
#164
opened Sep 1, 2026 by
hhzhang16
•
5/5
Loading…
docs: mntnsCompatMode is a dump-time setting, and the RKE2 mount-v2 issue
#149
opened Aug 31, 2026 by
yuanjiewei
Contributor
Loading…
fix(agent): validate a pre-existing artifact before adopting it
#148
opened Aug 31, 2026 by
yuanjiewei
Contributor
Loading…
fix(agent): fail the checkpoint when overlay rootfs-diff capture fails
#147
opened Aug 31, 2026 by
yuanjiewei
Contributor
Loading…
feat: publish what a checkpoint was captured on
#141
opened Aug 31, 2026 by
leeZardNav
Collaborator
Loading…
feat: refuse incompatible restores before CRIU
#140
opened Aug 31, 2026 by
leeZardNav
Collaborator
Loading…
6 of 7 tasks
perf(snapshot): remove duplicate CustomStorage restore prefetch
#121
opened Aug 26, 2026 by
hhzhang16
•
4/5
Loading…
Previous Next
ProTip!
Follow long discussions with comments:>50.